logmlc
LOGMLC
Logistic MultiClass Linear Classifier (Multinomial Logit)
W = LOGMLC(A)
W = LOGMLC(A, LABLIST_NAMES)
Input  A  Dataset  LABLISTNAMES  The character array of additional labelings which priors (along with the current labeling prior) have to be taken into account to compute object weights. It is useful if there are object subgroups which abundances in the (optional; default: '') 
Output  W  Logistic MultiClass Linear Classifier 
Description Computation of the linear classifier for the dataset A by maximizing the likelihood of the assumed posterior probalility model
p(cx) = exp(w_c'x + b_c)/(exp(w_1'x + b_1) + exp(w_2'x + b_2) + ...)
Differences from the LOGLC 1) Genuine multiclass classification. All weights are optimized simultaneously. 2) More careful Newtonian optimization procedure. 3) The use of Cholesky factorization instead of pinv for Hessian inversion. See also
mappings, loglc, This file has been automatically generated. If badly readable, use the helpcommand in Matlab. 
